Commit
·
0cad1a1
1
Parent(s):
d6268bc
Update app.py
Browse files
app.py
CHANGED
@@ -1,95 +1,48 @@
|
|
1 |
import gradio as gr
|
2 |
from transformers import pipeline
|
3 |
-
|
4 |
-
import moviepy.editor as mp
|
5 |
-
import numpy as np
|
6 |
-
import os
|
7 |
-
|
8 |
-
# Étape 1: Configurez vos pipelines
|
9 |
-
model1 = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
|
10 |
-
#model2 = pipeline("summarization", model="ainize/kobart-news")
|
11 |
-
#model3 = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-en-pt")
|
12 |
-
#model4 = pipeline("text-to-speech", model="microsoft/speecht5_tts")
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
def process_video(video):
|
21 |
-
|
22 |
-
if not os.path.exists("/main/images/"):
|
23 |
-
os.makedirs("/main/images/")
|
24 |
|
|
|
|
|
|
|
|
|
25 |
# Ouvrir la vidéo
|
26 |
-
cap = cv2.VideoCapture(video)
|
27 |
-
if not cap.isOpened():
|
28 |
-
print("Erreur lors de l'ouverture de la vidéo.")
|
29 |
-
return
|
30 |
-
|
31 |
-
# Fréquence d'images de la vidéo
|
32 |
fps = int(cap.get(cv2.CAP_PROP_FPS))
|
33 |
-
|
34 |
-
# Nombre total d'images dans la vidéo
|
35 |
-
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
36 |
-
|
37 |
-
# Calculer le nombre d'images à sauter pour obtenir une image toutes les demi-secondes
|
38 |
-
frames_to_skip = int(fps * interval)
|
39 |
-
|
40 |
-
count = 0
|
41 |
-
for i in range(0, total_frames, frames_to_skip):
|
42 |
-
cap.set(cv2.CAP_PROP_POS_FRAMES, i)
|
43 |
-
ret, frame = cap.read()
|
44 |
-
|
45 |
-
# Si la lecture a réussi, enregistrez l'image
|
46 |
-
if ret:
|
47 |
-
output_path = os.path.join("/main/images/", f"frame_{count}.jpg")
|
48 |
-
cv2.imwrite(output_path, frame)
|
49 |
-
count += 1
|
50 |
-
cap.release()
|
51 |
-
|
52 |
-
fichiers = os.listdir("/main/images/")
|
53 |
-
output_texts = []
|
54 |
-
|
55 |
-
for fichier in fichiers:
|
56 |
|
57 |
-
|
58 |
-
|
59 |
-
chemin_complet = os.path.join(chemin_dossier, fichier)
|
60 |
-
model1_output = model1(image)
|
61 |
-
output_texts.append(model1_output["generated_text"])
|
62 |
-
|
63 |
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
#model1_output = model1(image)
|
69 |
-
|
70 |
-
# Étape 4: Utiliser le modèle 2
|
71 |
-
#model2_output = model2(model1_output["generated_text"])
|
72 |
-
|
73 |
-
# Étape 5: Utiliser le modèle 3
|
74 |
-
#model3_output = model3(model2_output["generated_text"])
|
75 |
|
76 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
|
|
78 |
|
79 |
-
#
|
80 |
-
|
81 |
|
82 |
-
#
|
83 |
-
|
84 |
-
|
85 |
-
return
|
86 |
|
87 |
-
# Créer une interface gradio
|
88 |
iface = gr.Interface(
|
89 |
-
fn=
|
90 |
-
inputs=gr.inputs.Video(label="
|
91 |
outputs="text",
|
92 |
-
live=
|
93 |
)
|
94 |
|
95 |
-
|
|
|
|
1 |
import gradio as gr
|
2 |
from transformers import pipeline
|
3 |
+
import cv2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
5 |
+
def video_to_descriptions(video):
|
6 |
+
# Charger le modèle via pipeline
|
7 |
+
model = pipeline('image-to-text', model='nlpconnect/vit-gpt2-image-captioning')
|
8 |
+
|
9 |
# Ouvrir la vidéo
|
10 |
+
cap = cv2.VideoCapture(video.name)
|
|
|
|
|
|
|
|
|
|
|
11 |
fps = int(cap.get(cv2.CAP_PROP_FPS))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
+
descriptions = []
|
14 |
+
frame_count = 0
|
|
|
|
|
|
|
|
|
15 |
|
16 |
+
while True:
|
17 |
+
ret, frame = cap.read()
|
18 |
+
if not ret:
|
19 |
+
break
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
+
# Extraire une image toutes les demi-secondes
|
22 |
+
if frame_count % (fps // 2) == 0:
|
23 |
+
# Convertir l'image en RGB
|
24 |
+
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
25 |
+
# Obtenir la description de l'image
|
26 |
+
outputs = model(frame_rgb)
|
27 |
+
description = outputs[0]['describe-text']
|
28 |
+
descriptions.append(description)
|
29 |
|
30 |
+
frame_count += 1
|
31 |
|
32 |
+
# Fermer le lecteur vidéo
|
33 |
+
cap.release()
|
34 |
|
35 |
+
# Concaténer les descriptions
|
36 |
+
concatenated_descriptions = " ".join(descriptions)
|
37 |
+
|
38 |
+
return concatenated_descriptions
|
39 |
|
|
|
40 |
iface = gr.Interface(
|
41 |
+
fn=video_to_descriptions,
|
42 |
+
inputs=gr.inputs.Video(type="file", label="Importez une vidéo"),
|
43 |
outputs="text",
|
44 |
+
live=False
|
45 |
)
|
46 |
|
47 |
+
if __name__ == "__app__":
|
48 |
+
iface.launch()
|